cleanText is now method

Author: Nito

README.md

@@ -40,8 +40,8 @@ var_dump($eld->detect('Hola, cómo te llamas?'));
 print $eld->detect('Hola, cómo te llamas?')->language;
 // 'es'
 
-// cleanText = true: Removes Urls, .com domains, emails, alphanumerical & numbers; from input text
-$eld->cleanText = true; // Default is false
+// cleanText(true): Removes Urls, .com domains, emails, alphanumerical & numbers; from input text
+$eld->cleanText(true); // Default is false
 ```
 
 - To reduce the languages to be detected, there are 3 different options, they only need to be executed once. (Check available [languages](#languages) below)

demo.php

@@ -19,8 +19,8 @@
 // object( language => null|string, scores => null|array, isReliable() => bool )
 var_dump($result->language);
 
-// cleanText = true: Removes Urls, .com domains, emails, alphanumerical & numbers
-$eld->cleanText = true; // Default is false
+// When cleanText(true) Removes Urls, .com domains, emails, alphanumerical & numbers
+$eld->cleanText(true); // Default is false
 
 /*
  To reduce the languages to be detected, there are 3 different options, they only need to be executed once.

src/LanguageDetector.php

@@ -16,7 +16,7 @@
  */
 class LanguageDetector extends LanguageData
 {
-    public bool $cleanText = false;
+    protected bool $doCleanText = false;
     private array $wordStart;
 
     public function __construct(?string $ngramsFile = null)
@@ -32,10 +32,11 @@ public function __construct(?string $ngramsFile = null)
      */
     public function detect(string $text): LanguageResult
     {
-        if ($this->cleanText) {
+        if ($this->doCleanText) {
             // Removes Urls, emails, alphanumerical & numbers
             $text = $this->getCleanText($text);
         }
+
         $text = $this->normalizeText($text);
         $textNgrams = $this->getByteNgrams($text);
         $numNgrams = count($textNgrams);
@@ -52,6 +53,11 @@ public function detect(string $text): LanguageResult
         return new LanguageResult();
     }
 
+    public function cleanText(bool $bool): void
+    {
+        $this->doCleanText = $bool; // Already cast in the argument
+    }
+
     /**
      * Removes parts of a string, that may be considered as "noise" for language detection
      */
@@ -169,4 +175,5 @@ protected function calculateScores(array $textNgrams, int $numNgrams): array
 
         return $results;
     }
+
 }

tests/tests.php

@@ -61,7 +61,7 @@
     }
 });
 
-$tests->addTest('Clean text', function () {
+$tests->addTest('getCleanText function', function () {
     $eld = new Nitotm\Eld\LanguageDetector();
 
     $text = "https://www.google.com/\n" .
@@ -76,6 +76,22 @@
     }
 });
 
+$tests->addTest('Clean text option', function () {
+    $eld = new Nitotm\Eld\LanguageDetector();
+    $eld->cleanText(true);
+
+    $text = "https://www.google.com/\n" .
+        "mail@gmail.com\n" .
+        "google.com/search?q=search&source=hp\n" .
+        "12345 A12345\n";
+
+    $result = $eld->detect($text);
+
+    if ($result->language !== NULL) {
+        throw new Exception("Expected: NULL, but got " . json_encode($result));
+    }
+});
+
 $tests->addTest('Check minimum confidence', function () {
     $eld = new Nitotm\Eld\LanguageDetector('ngramsM60.php');
 
@@ -204,4 +220,4 @@
     }
 });
 
-$tests->run();
+$tests->run();